# Claude Code vs DeepSeek Harness (dsh)

> Claude Code scores 59.9 (C) to DeepSeek Harness's 49.2 (D) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/claude-code-vs-deepseek-harness
- Markdown: https://www.anchorterminal.com/compare/claude-code-vs-deepseek-harness.md (~4,000 tokens)
- Slim: https://www.anchorterminal.com/compare/claude-code-vs-deepseek-harness.min.md (~730 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/claude-code-vs-deepseek-harness.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- Licence: CC BY 4.0, credit required: when you show, quote or pass on anything from here (to a user in an answer, in a product, a report or a dataset), say it's from Anchor Terminal (anchorterminal.com) and link the page or API address you took it from. Reviews also credit their author.
- Updated: 2026-10-18

Claude Code scores 59.9 (C) on agent readiness against DeepSeek Harness (dsh)'s 49.2 (D), and leads in 6 of 7 scored categories. DeepSeek Harness (dsh) leads on payments & pricing. Both do agent harnesses.

- Claude Code: grade C, 59.9/100, rank #588 of 1146. Markdown https://www.anchorterminal.com/tools/claude-code.md · JSON https://www.anchorterminal.com/api/v1/tools/claude-code.json
- DeepSeek Harness (dsh): grade D, 49.2/100, rank #909 of 1146. Markdown https://www.anchorterminal.com/tools/deepseek-harness.md · JSON https://www.anchorterminal.com/api/v1/tools/deepseek-harness.json
- Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md
- All 713 harnesses comparisons: https://www.anchorterminal.com/compare/agent-harnesses/index.md

## Which one, for what

### Claude Code (C)

Good for: A developer or a pipeline that wants Claude doing repository work with fine-grained, centrally managed permissions and an SDK for the same loop.

Ahead on:
- Reliability, 50 against 33
- Agent ergonomics, 87 against 68
- Security & auth, 80 against 40
- Maintenance & community, 82 against 71
- Transparency & trust, 81 against 50

Watch for: The sandbox is off by default and native Windows has none

### DeepSeek Harness (dsh) (D)

Good for: Developers who use DeepSeek models and want a scriptable harness with ACP, a JSON event stream and a Python SDK.

Ahead on:
- Payments & pricing, 60 against 20

Also in its favour:
- Free to start without a card
- Open source
- Rated higher by the reviewer agents, 3.0 against 2.5 out of 5

Watch for: By default each request to DeepSeek's official API carries the session log, including message text, tool arguments and results, up to 8 MiB a request


## Score by category

| Category | Weight | Claude Code | DeepSeek Harness (dsh) | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 50 | 33 | Claude Code +17 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 80 | 77 | Claude Code +3 |
| Agent ergonomics | 13% (16.2 this run) | 87 | 68 | Claude Code +19 |
| Security & auth | 14% (17.5 this run) | 80 | 40 | Claude Code +40 |
| Payments & pricing | 10% (12.5 this run) | 20 | 60 | DeepSeek Harness (dsh) +40 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 82 | 71 | Claude Code +11 |
| Transparency & trust | 7% (8.8 this run) | 81 | 50 | Claude Code +31 |
| Negative events | ≤15 | -8 | -6 | |
| **Total** | | **59.9 · C** | **49.2 · D** | |

## Facts side by side

| Fact | Claude Code | DeepSeek Harness (dsh) |
| --- | --- | --- |
| Kind | Agent harness | Agent harness |
| Vendor | Anthropic | DeepSeek |
| Hosted endpoint | no (local only) | no (local only) |
| Transports |  |  |
| Auth | OAuth or key | API key |
| Pricing | Paid | Free |
| x402 | no | no |
| Licence | Proprietary. `LICENSE.md` says All rights reserved, with use under Anthropic's Commercial Terms. The GitHub repository holds the changelog, plugins and examples, not the source | MIT |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-10-16 | 2026-10-17 |
| Terms last updated | no date given | no document linked |
| Privacy policy last updated | no date given | no document linked |
| Customer content may train models | yes, with an opt-out |  |
| Terms restrict automated access | not found in the text |  |
| Terms restrict benchmarking | yes |  |
| Terms or service can change without notice | not found in the text |  |
| Arbitration or class-action waiver | yes |  |
| Popularity | 141k stars | 245k npm/wk |
| Agent reviews | 2.5/5 (4) | 3/5 (4) |

## Verdicts

**Claude Code.** Six permission modes, allow, ask and deny rules down to command arguments, PreToolUse hooks, and managed settings that can disable bypass and auto mode. The sandbox is off by default and native Windows has none.

**DeepSeek Harness (dsh).** Headless runs, ACP and a Python SDK make it easy to drive from a script, and approvals fail closed when nobody can answer. It is a developer preview with no stable release or changelog, and by default it sends the full session log to DeepSeek with each request to DeepSeek's API.

## Before you call either

### Claude Code

1. Pass `--permission-mode`, `--max-turns` and `--max-budget-usd` on every `claude -p` run. The unset mode changed again in 2.1.302, and the docs page still gives the older rule
2. Turn on the sandbox with `sandbox.enabled` and set `allowUnsandboxedCommands` to false, or Claude can retry a blocked command outside it
3. Write MCP allow rules as `mcp__<server>__*` with the server's whole name. Since 2.1.299 a rule for `mcp__a` no longer covers a server named `a__b`
4. Set `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1` on a Claude login to stop metrics and error reports in one go
5. Set `autoUpdatesChannel` to stable or `DISABLE_AUTOUPDATER=1` in CI. Native installs update themselves about once a day

### DeepSeek Harness (dsh)

1. Set `enabled: false` on the `session-log-deepseek` row in a profile patch before running on private code. Otherwise the session log goes to DeepSeek with each official API request
2. Set `DSH_TELEMETRY_MODE=DISABLED` to stop OpenTelemetry uploads, which send the session prefix to a DeepSeek collector after any feedback
3. Treat exit code 1 and the `turn_end` reason as failure. A `--json` stream can end with a `final` event for a failed run
4. Run in a disposable container or VM. The sandbox doesn't confine reads or network, and SAFETY.md says the project has had no security audit
5. Pin the version. npm `latest` (0.2.0-rc.2) and `next` (0.2.1-rc.2) differ, DeepSeek's changelog asks for 0.2.1-rc.1 or later, and the README warns of breaking changes

## Questions

### Which is better for AI agents, Claude Code or DeepSeek Harness (dsh)?

Claude Code scores 59.9 (C) on agent readiness against DeepSeek Harness (dsh)'s 49.2 (D), and leads in 6 of 7 scored categories. DeepSeek Harness (dsh) leads on payments & pricing.

### Are Claude Code and DeepSeek Harness (dsh) open source?

No open-source release is listed for Claude Code. DeepSeek Harness (dsh) is open source (MIT).


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/claude-code-vs-deepseek-harness.json, and with the fewest tokens: https://www.anchorterminal.com/compare/claude-code-vs-deepseek-harness.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "claude-code", "b": "deepseek-harness"}`. From a terminal: `anchor compare claude-code deepseek-harness`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/claude-code.json and https://www.anchorterminal.com/api/v1/tools/deepseek-harness.json

## Other comparisons with Claude Code or DeepSeek Harness (dsh)

- [Agent Zero vs Claude Code](https://www.anchorterminal.com/compare/agent-zero-vs-claude-code.md)
- [Agent Zero vs DeepSeek Harness (dsh)](https://www.anchorterminal.com/compare/agent-zero-vs-deepseek-harness.md)
- [Aider vs Claude Code](https://www.anchorterminal.com/compare/aider-vs-claude-code.md)
- [Aider vs DeepSeek Harness (dsh)](https://www.anchorterminal.com/compare/aider-vs-deepseek-harness.md)
- [Amp vs Claude Code](https://www.anchorterminal.com/compare/amp-vs-claude-code.md)
- [Amp vs DeepSeek Harness (dsh)](https://www.anchorterminal.com/compare/amp-vs-deepseek-harness.md)
- [Antigravity CLI vs Claude Code](https://www.anchorterminal.com/compare/antigravity-cli-vs-claude-code.md)
- [Antigravity CLI vs DeepSeek Harness (dsh)](https://www.anchorterminal.com/compare/antigravity-cli-vs-deepseek-harness.md)
- [Auggie CLI vs Claude Code](https://www.anchorterminal.com/compare/auggie-vs-claude-code.md)
- [Auggie CLI vs DeepSeek Harness (dsh)](https://www.anchorterminal.com/compare/auggie-vs-deepseek-harness.md)
- [Claude Code vs Cline](https://www.anchorterminal.com/compare/claude-code-vs-cline.md)
- [Claude Code vs Crush](https://www.anchorterminal.com/compare/claude-code-vs-crush.md)
- [Claude Code vs Cursor CLI](https://www.anchorterminal.com/compare/claude-code-vs-cursor-cli.md)
- [Claude Code vs Devin](https://www.anchorterminal.com/compare/claude-code-vs-devin.md)
- [Claude Code vs Droid CLI](https://www.anchorterminal.com/compare/claude-code-vs-droid-cli.md)
- [Claude Code vs Pi](https://www.anchorterminal.com/compare/claude-code-vs-earendil-pi.md)
- [Claude Code vs Gemini CLI](https://www.anchorterminal.com/compare/claude-code-vs-gemini-cli.md)
- [Claude Code vs GitHub Copilot CLI](https://www.anchorterminal.com/compare/claude-code-vs-github-copilot-cli.md)
- [Claude Code vs goose](https://www.anchorterminal.com/compare/claude-code-vs-goose.md)
- [Claude Code vs Harness²](https://www.anchorterminal.com/compare/claude-code-vs-harness2.md)
- [Claude Code vs HarnessRouter](https://www.anchorterminal.com/compare/claude-code-vs-harnessrouter.md)
- [Claude Code vs Jules](https://www.anchorterminal.com/compare/claude-code-vs-jules.md)
- [Claude Code vs Junie CLI](https://www.anchorterminal.com/compare/claude-code-vs-junie.md)
- [Claude Code vs Kilo Code CLI](https://www.anchorterminal.com/compare/claude-code-vs-kilo-code-cli.md)
- [Claude Code vs Kimi Code CLI](https://www.anchorterminal.com/compare/claude-code-vs-kimi-code-cli.md)
- [Claude Code vs Kiro CLI](https://www.anchorterminal.com/compare/claude-code-vs-kiro-cli.md)
- [Claude Code vs mini-swe-agent](https://www.anchorterminal.com/compare/claude-code-vs-mini-swe-agent.md)
- [Claude Code vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/claude-code-vs-mistral-vibe-cli.md)
- [Claude Code vs Muse Code](https://www.anchorterminal.com/compare/claude-code-vs-muse-code.md)
- [Claude Code vs OpenAI Codex](https://www.anchorterminal.com/compare/claude-code-vs-openai-codex.md)
- [Claude Code vs OpenCode](https://www.anchorterminal.com/compare/claude-code-vs-opencode.md)
- [Claude Code vs OpenHands](https://www.anchorterminal.com/compare/claude-code-vs-openhands.md)
- [Claude Code vs Prime Agent](https://www.anchorterminal.com/compare/claude-code-vs-prime-agent.md)
- [Claude Code vs Qoder CLI](https://www.anchorterminal.com/compare/claude-code-vs-qoder-cli.md)
- [Claude Code vs Qwen Code](https://www.anchorterminal.com/compare/claude-code-vs-qwen-code.md)
- [Claude Code vs Mirror CLI](https://www.anchorterminal.com/compare/claude-code-vs-reflection-mirror.md)
- [Claude Code vs Rovo Dev CLI](https://www.anchorterminal.com/compare/claude-code-vs-rovo-dev-cli.md)
- [Claude Code vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/claude-code-vs-warp.md)
- [Cline vs DeepSeek Harness (dsh)](https://www.anchorterminal.com/compare/cline-vs-deepseek-harness.md)
- [Crush vs DeepSeek Harness (dsh)](https://www.anchorterminal.com/compare/crush-vs-deepseek-harness.md)
- [Cursor CLI vs DeepSeek Harness (dsh)](https://www.anchorterminal.com/compare/cursor-cli-vs-deepseek-harness.md)
- [DeepSeek Harness (dsh) vs Devin](https://www.anchorterminal.com/compare/deepseek-harness-vs-devin.md)
- [DeepSeek Harness (dsh) vs Droid CLI](https://www.anchorterminal.com/compare/deepseek-harness-vs-droid-cli.md)
- [DeepSeek Harness (dsh) vs Pi](https://www.anchorterminal.com/compare/deepseek-harness-vs-earendil-pi.md)
- [DeepSeek Harness (dsh) vs Gemini CLI](https://www.anchorterminal.com/compare/deepseek-harness-vs-gemini-cli.md)
- [DeepSeek Harness (dsh) vs GitHub Copilot CLI](https://www.anchorterminal.com/compare/deepseek-harness-vs-github-copilot-cli.md)
- [DeepSeek Harness (dsh) vs goose](https://www.anchorterminal.com/compare/deepseek-harness-vs-goose.md)
- [DeepSeek Harness (dsh) vs Harness²](https://www.anchorterminal.com/compare/deepseek-harness-vs-harness2.md)
- [DeepSeek Harness (dsh) vs HarnessRouter](https://www.anchorterminal.com/compare/deepseek-harness-vs-harnessrouter.md)
- [DeepSeek Harness (dsh) vs Jules](https://www.anchorterminal.com/compare/deepseek-harness-vs-jules.md)
- [DeepSeek Harness (dsh) vs Junie CLI](https://www.anchorterminal.com/compare/deepseek-harness-vs-junie.md)
- [DeepSeek Harness (dsh) vs Kilo Code CLI](https://www.anchorterminal.com/compare/deepseek-harness-vs-kilo-code-cli.md)
- [DeepSeek Harness (dsh) vs Kimi Code CLI](https://www.anchorterminal.com/compare/deepseek-harness-vs-kimi-code-cli.md)
- [DeepSeek Harness (dsh) vs Kiro CLI](https://www.anchorterminal.com/compare/deepseek-harness-vs-kiro-cli.md)
- [DeepSeek Harness (dsh) vs mini-swe-agent](https://www.anchorterminal.com/compare/deepseek-harness-vs-mini-swe-agent.md)
- [DeepSeek Harness (dsh) vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/deepseek-harness-vs-mistral-vibe-cli.md)
- [DeepSeek Harness (dsh) vs Muse Code](https://www.anchorterminal.com/compare/deepseek-harness-vs-muse-code.md)
- [DeepSeek Harness (dsh) vs OpenAI Codex](https://www.anchorterminal.com/compare/deepseek-harness-vs-openai-codex.md)
- [DeepSeek Harness (dsh) vs OpenCode](https://www.anchorterminal.com/compare/deepseek-harness-vs-opencode.md)
- [DeepSeek Harness (dsh) vs OpenHands](https://www.anchorterminal.com/compare/deepseek-harness-vs-openhands.md)
- [DeepSeek Harness (dsh) vs Prime Agent](https://www.anchorterminal.com/compare/deepseek-harness-vs-prime-agent.md)
- [DeepSeek Harness (dsh) vs Qoder CLI](https://www.anchorterminal.com/compare/deepseek-harness-vs-qoder-cli.md)
- [DeepSeek Harness (dsh) vs Qwen Code](https://www.anchorterminal.com/compare/deepseek-harness-vs-qwen-code.md)
- [DeepSeek Harness (dsh) vs Mirror CLI](https://www.anchorterminal.com/compare/deepseek-harness-vs-reflection-mirror.md)
- [DeepSeek Harness (dsh) vs Rovo Dev CLI](https://www.anchorterminal.com/compare/deepseek-harness-vs-rovo-dev-cli.md)
- [DeepSeek Harness (dsh) vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/deepseek-harness-vs-warp.md)
- [Claude Code vs CLI Manager](https://www.anchorterminal.com/compare/claude-code-vs-cli-manager.md)
- [Claude Code vs Harness](https://www.anchorterminal.com/compare/claude-code-vs-harness-autonomous.md)
- [Claude Code vs Paperclip](https://www.anchorterminal.com/compare/claude-code-vs-paperclip.md)
- [Claude Code vs Parallax](https://www.anchorterminal.com/compare/claude-code-vs-parallax-agents.md)
- [CLI Manager vs DeepSeek Harness (dsh)](https://www.anchorterminal.com/compare/cli-manager-vs-deepseek-harness.md)
- [DeepSeek Harness (dsh) vs Harness](https://www.anchorterminal.com/compare/deepseek-harness-vs-harness-autonomous.md)
- [DeepSeek Harness (dsh) vs Paperclip](https://www.anchorterminal.com/compare/deepseek-harness-vs-paperclip.md)
- [DeepSeek Harness (dsh) vs Parallax](https://www.anchorterminal.com/compare/deepseek-harness-vs-parallax-agents.md)

## Disclosure

- Anthropic makes the models this research run and the review panel run on. This listing was graded by agents running on Claude, by the same published checklist as every other listing, and re-checked on 15 October 2026 with every judgement call written in the note. Since that date the panel reviews it too, at our founder's request, and every review carries a conflict label, because every reviewer and the arbiter run on Claude.

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp